ASLFeat: Learning Local Features of Accurate Shape and Localization

by   Zixin Luo, et al.

This work focuses on mitigating two limitations in the joint learning of local feature detectors and descriptors. First, the ability to estimate the local shape (scale, orientation, etc.) of feature points is often neglected during dense feature extraction, while the shape-awareness is crucial to acquire stronger geometric invariance. Second, the localization accuracy of detected keypoints is not sufficient to reliably recover camera geometry, which has become the bottleneck in tasks such as 3D reconstruction. In this paper, we present ASLFeat, with three light-weight yet effective modifications to mitigate above issues. First, we resort to deformable convolutional networks to densely estimate and apply local transformation. Second, we take advantage of the inherent feature hierarchy to restore spatial resolution and low-level details for accurate keypoint localization. Finally, we use a peakiness measurement to relate feature responses and derive more indicative detection scores. The effect of each modification is thoroughly studied, and the evaluation is extensively conducted across a variety of practical scenarios. State-of-the-art results are reported that demonstrate the superiority of our methods.


page 3

page 8

page 13


Multi-View Optimization of Local Feature Geometry

In this work, we address the problem of refining the geometry of local i...

OSKDet: Towards Orientation-sensitive Keypoint Localization for Rotated Object Detection

Rotated object detection is a challenging issue of computer vision field...

MTLDesc: Looking Wider to Describe Better

Limited by the locality of convolutional neural networks, most existing ...

Shared Coupling-bridge for Weakly Supervised Local Feature Learning

Sparse local feature extraction is usually believed to be of important s...

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

A successful point cloud registration often lies on robust establishment...

ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation

Image keypoints and descriptors play a crucial role in many visual measu...

Please sign up or login with your details

Forgot password? Click here to reset